摘要
传统算法由于应用技术的缺陷,存在通信数据校正时间长、校正精度差的问题,因此提出基于神经网络的舰船通信数据实时校正算法。对采集的舰船通信数据进行归一化与切片预处理,以此为基础,训练神经网络模型,并更新模型参数,将测试通信数据集合输入至训练好的神经网络模型中,输出结果即为通信误差数据检测结果,采用线性稳态数据协调原理,计算通信数据校正值,将校正值与通信数据进行加和运算,从而实现了舰船通信数据的实时校正。实验数据表明,与传统算法相比较,本文算法通信数据校正时间大幅度缩短,校正精度大幅度提高,充分证实本文算法的数据校正效果更好。
Due to the defects of application technology,the existing algorithms have the problems of long communication data correction time and poor correction accuracy.Therefore,the real-time correction algorithm of ship communication data based on neural network is proposed.After normalizing and slicing the collected ship communication data,the neural network model is trained,and the model parameters are updated.The test communication data set is input into the trained neural network model,and the output result is the detection result of communication error data.Based on the principle of linear steady-state data coordination,the correction value of communication data is calculated,and the correction value and communication data are added,thus realizing the real-time correction of ship communication data.The experimental data show that:compared with the existing algorithms,the proposed algorithm greatly shortens the communication data correction time and improves the correction accuracy,which fully proves that the proposed algorithm has better data correction effect.
作者
张坚实
王东
ZHANG Jian-shi;WANG Dong(School of Changchun Polytechnic,Changchun 130033,China)
出处
《舰船科学技术》
北大核心
2021年第14期121-123,共3页
Ship Science and Technology
基金
工业和信息化职业教育教学指导委员会课题(GXHZW20201607)
关键词
神经网络
舰船
通信数据
实时校正
neural network
warship
communication data
real time correcting
